If you want to fully grasp machine learning,and avoid mistakes, you’ll need to be familiar with math at some level. You’ll find it in papers and textbooks as well as libraries/frameworks. With a targeted approach, and the right frame of mind, you can tackle the math necessary for machine learning. If you didn’t get along with math in high school then don’t worry, this talk will be down-to-earth and approachable, and has been designed with you in mind.

This talk will cover practical mathematical concepts featured in machine learning, presented in a very accessible, visual manner. Let’s break down any intimidation or hesitation towards approaching the math in machine learning.

**Required audience experience**

ANY level of mathematical knowledge is acceptable. (If you have more than an A-level/Higher in the subject, this would be more of a refresher.)

**Objective of the talk**

This talk will break down barriers to basic mathematical concepts within machine learning, including:

- Notation and terminology (decode formulae/language in papers)
- Matrices and their manipulation
- Functions and graphs (visualise algebra)
- Rate of change (useful theories from calculus)

Location: **Auditorium**
Date: **October 15, 2018**
Time: **12:35 pm - 1:20 pm**
Kate Kilgour, University of Dundee